Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 22-CLT-HP
    4. 74235
    Prev
    Next
    INDEX
    Explanations

    software code contexts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ExecuteAsync
    -0.66
    ьаж
    -0.52
    DebuggerNonUser
    -0.49
     ganas
    -0.47
     Roskov
    -0.46
     taskId
    -0.46
    DataTypes
    -0.45
    Ặ
    -0.45
     بيها
    -0.45
    libft
    -0.45
    POSITIVE LOGITS
     Ir
    0.55
     nose
    0.48
     jLabel
    0.47
    birth
    0.47
    POA
    0.45
    Ir
    0.44
    upar
    0.44
    burn
    0.44
     birth
    0.43
    ImGui
    0.42
    Activations Density 0.011%

    No Known Activations